US7518225B2 - Chip system architecture for performance enhancement, power reduction and cost reduction - Google Patents
Chip system architecture for performance enhancement, power reduction and cost reduction Download PDFInfo
- Publication number
- US7518225B2 US7518225B2 US11/538,567 US53856706A US7518225B2 US 7518225 B2 US7518225 B2 US 7518225B2 US 53856706 A US53856706 A US 53856706A US 7518225 B2 US7518225 B2 US 7518225B2
- Authority
- US
- United States
- Prior art keywords
- chip
- layered chip
- layered
- carrier package
- stack
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active, expires
Links
Images
Classifications
-
- H—ELECTRICITY
- H01—ELECTRIC ELEMENTS
- H01L—SEMICONDUCTOR DEVICES NOT COVERED BY CLASS H10
- H01L25/00—Assemblies consisting of a plurality of individual semiconductor or other solid state devices ; Multistep manufacturing processes thereof
- H01L25/03—Assemblies consisting of a plurality of individual semiconductor or other solid state devices ; Multistep manufacturing processes thereof all the devices being of a type provided for in the same subgroup of groups H01L27/00 - H01L33/00, or in a single subclass of H10K, H10N, e.g. assemblies of rectifier diodes
- H01L25/04—Assemblies consisting of a plurality of individual semiconductor or other solid state devices ; Multistep manufacturing processes thereof all the devices being of a type provided for in the same subgroup of groups H01L27/00 - H01L33/00, or in a single subclass of H10K, H10N, e.g. assemblies of rectifier diodes the devices not having separate containers
- H01L25/065—Assemblies consisting of a plurality of individual semiconductor or other solid state devices ; Multistep manufacturing processes thereof all the devices being of a type provided for in the same subgroup of groups H01L27/00 - H01L33/00, or in a single subclass of H10K, H10N, e.g. assemblies of rectifier diodes the devices not having separate containers the devices being of a type provided for in group H01L27/00
- H01L25/0657—Stacked arrangements of devices
-
- H—ELECTRICITY
- H01—ELECTRIC ELEMENTS
- H01L—SEMICONDUCTOR DEVICES NOT COVERED BY CLASS H10
- H01L25/00—Assemblies consisting of a plurality of individual semiconductor or other solid state devices ; Multistep manufacturing processes thereof
- H01L25/03—Assemblies consisting of a plurality of individual semiconductor or other solid state devices ; Multistep manufacturing processes thereof all the devices being of a type provided for in the same subgroup of groups H01L27/00 - H01L33/00, or in a single subclass of H10K, H10N, e.g. assemblies of rectifier diodes
- H01L25/04—Assemblies consisting of a plurality of individual semiconductor or other solid state devices ; Multistep manufacturing processes thereof all the devices being of a type provided for in the same subgroup of groups H01L27/00 - H01L33/00, or in a single subclass of H10K, H10N, e.g. assemblies of rectifier diodes the devices not having separate containers
- H01L25/065—Assemblies consisting of a plurality of individual semiconductor or other solid state devices ; Multistep manufacturing processes thereof all the devices being of a type provided for in the same subgroup of groups H01L27/00 - H01L33/00, or in a single subclass of H10K, H10N, e.g. assemblies of rectifier diodes the devices not having separate containers the devices being of a type provided for in group H01L27/00
- H01L25/0652—Assemblies consisting of a plurality of individual semiconductor or other solid state devices ; Multistep manufacturing processes thereof all the devices being of a type provided for in the same subgroup of groups H01L27/00 - H01L33/00, or in a single subclass of H10K, H10N, e.g. assemblies of rectifier diodes the devices not having separate containers the devices being of a type provided for in group H01L27/00 the devices being arranged next and on each other, i.e. mixed assemblies
-
- H—ELECTRICITY
- H01—ELECTRIC ELEMENTS
- H01L—SEMICONDUCTOR DEVICES NOT COVERED BY CLASS H10
- H01L25/00—Assemblies consisting of a plurality of individual semiconductor or other solid state devices ; Multistep manufacturing processes thereof
- H01L25/18—Assemblies consisting of a plurality of individual semiconductor or other solid state devices ; Multistep manufacturing processes thereof the devices being of types provided for in two or more different subgroups of the same main group of groups H01L27/00 - H01L33/00, or in a single subclass of H10K, H10N
-
- H—ELECTRICITY
- H01—ELECTRIC ELEMENTS
- H01L—SEMICONDUCTOR DEVICES NOT COVERED BY CLASS H10
- H01L2225/00—Details relating to assemblies covered by the group H01L25/00 but not provided for in its subgroups
- H01L2225/03—All the devices being of a type provided for in the same subgroup of groups H01L27/00 - H01L33/648 and H10K99/00
- H01L2225/04—All the devices being of a type provided for in the same subgroup of groups H01L27/00 - H01L33/648 and H10K99/00 the devices not having separate containers
- H01L2225/065—All the devices being of a type provided for in the same subgroup of groups H01L27/00 - H01L33/648 and H10K99/00 the devices not having separate containers the devices being of a type provided for in group H01L27/00
- H01L2225/06503—Stacked arrangements of devices
- H01L2225/06513—Bump or bump-like direct electrical connections between devices, e.g. flip-chip connection, solder bumps
-
- H—ELECTRICITY
- H01—ELECTRIC ELEMENTS
- H01L—SEMICONDUCTOR DEVICES NOT COVERED BY CLASS H10
- H01L2225/00—Details relating to assemblies covered by the group H01L25/00 but not provided for in its subgroups
- H01L2225/03—All the devices being of a type provided for in the same subgroup of groups H01L27/00 - H01L33/648 and H10K99/00
- H01L2225/04—All the devices being of a type provided for in the same subgroup of groups H01L27/00 - H01L33/648 and H10K99/00 the devices not having separate containers
- H01L2225/065—All the devices being of a type provided for in the same subgroup of groups H01L27/00 - H01L33/648 and H10K99/00 the devices not having separate containers the devices being of a type provided for in group H01L27/00
- H01L2225/06503—Stacked arrangements of devices
- H01L2225/06517—Bump or bump-like direct electrical connections from device to substrate
-
- H—ELECTRICITY
- H01—ELECTRIC ELEMENTS
- H01L—SEMICONDUCTOR DEVICES NOT COVERED BY CLASS H10
- H01L2225/00—Details relating to assemblies covered by the group H01L25/00 but not provided for in its subgroups
- H01L2225/03—All the devices being of a type provided for in the same subgroup of groups H01L27/00 - H01L33/648 and H10K99/00
- H01L2225/04—All the devices being of a type provided for in the same subgroup of groups H01L27/00 - H01L33/648 and H10K99/00 the devices not having separate containers
- H01L2225/065—All the devices being of a type provided for in the same subgroup of groups H01L27/00 - H01L33/648 and H10K99/00 the devices not having separate containers the devices being of a type provided for in group H01L27/00
- H01L2225/06503—Stacked arrangements of devices
- H01L2225/06541—Conductive via connections through the device, e.g. vertical interconnects, through silicon via [TSV]
-
- H—ELECTRICITY
- H01—ELECTRIC ELEMENTS
- H01L—SEMICONDUCTOR DEVICES NOT COVERED BY CLASS H10
- H01L2225/00—Details relating to assemblies covered by the group H01L25/00 but not provided for in its subgroups
- H01L2225/03—All the devices being of a type provided for in the same subgroup of groups H01L27/00 - H01L33/648 and H10K99/00
- H01L2225/04—All the devices being of a type provided for in the same subgroup of groups H01L27/00 - H01L33/648 and H10K99/00 the devices not having separate containers
- H01L2225/065—All the devices being of a type provided for in the same subgroup of groups H01L27/00 - H01L33/648 and H10K99/00 the devices not having separate containers the devices being of a type provided for in group H01L27/00
- H01L2225/06503—Stacked arrangements of devices
- H01L2225/06572—Auxiliary carrier between devices, the carrier having an electrical connection structure
-
- H—ELECTRICITY
- H01—ELECTRIC ELEMENTS
- H01L—SEMICONDUCTOR DEVICES NOT COVERED BY CLASS H10
- H01L2225/00—Details relating to assemblies covered by the group H01L25/00 but not provided for in its subgroups
- H01L2225/03—All the devices being of a type provided for in the same subgroup of groups H01L27/00 - H01L33/648 and H10K99/00
- H01L2225/04—All the devices being of a type provided for in the same subgroup of groups H01L27/00 - H01L33/648 and H10K99/00 the devices not having separate containers
- H01L2225/065—All the devices being of a type provided for in the same subgroup of groups H01L27/00 - H01L33/648 and H10K99/00 the devices not having separate containers the devices being of a type provided for in group H01L27/00
- H01L2225/06503—Stacked arrangements of devices
- H01L2225/06589—Thermal management, e.g. cooling
-
- H—ELECTRICITY
- H01—ELECTRIC ELEMENTS
- H01L—SEMICONDUCTOR DEVICES NOT COVERED BY CLASS H10
- H01L23/00—Details of semiconductor or other solid state devices
- H01L23/58—Structural electrical arrangements for semiconductor devices not otherwise provided for, e.g. in combination with batteries
- H01L23/64—Impedance arrangements
- H01L23/642—Capacitive arrangements
-
- H—ELECTRICITY
- H01—ELECTRIC ELEMENTS
- H01L—SEMICONDUCTOR DEVICES NOT COVERED BY CLASS H10
- H01L2924/00—Indexing scheme for arrangements or methods for connecting or disconnecting semiconductor or solid-state bodies as covered by H01L24/00
- H01L2924/0001—Technical content checked by a classifier
- H01L2924/0002—Not covered by any one of groups H01L24/00, H01L24/00 and H01L2224/00
-
- H—ELECTRICITY
- H01—ELECTRIC ELEMENTS
- H01L—SEMICONDUCTOR DEVICES NOT COVERED BY CLASS H10
- H01L2924/00—Indexing scheme for arrangements or methods for connecting or disconnecting semiconductor or solid-state bodies as covered by H01L24/00
- H01L2924/15—Details of package parts other than the semiconductor or other solid state devices to be connected
- H01L2924/151—Die mounting substrate
- H01L2924/153—Connection portion
- H01L2924/1531—Connection portion the connection portion being formed only on the surface of the substrate opposite to the die mounting surface
- H01L2924/15311—Connection portion the connection portion being formed only on the surface of the substrate opposite to the die mounting surface being a ball array, e.g. BGA
Definitions
- This invention generally relates to a method for designing multi-core processing systems, and more specifically, to a method for combining two emerging technology areas: Systems On Package (SOP) and 3D technology.
- SOP Systems On Package
- FIG. 1 illustrates the above situation.
- a “core” 100 which comprises the processor 101 itself, and two additional cache levels 103 , 104 .
- the processor 101 is the logic-intensive circuitry.
- the L1 cache 102 is considered to be part of the processor 101 , since its access is part of the processor pipeline. As frequencies have gone up to multiple Ghz, the L1 102 has become too small to provide high hit rates. Therefore, an L1.5 103 cache level has been added to supplement the L1 102 .
- the L1.5 103 is also limited in size because it must be reasonably fast to accommodate the high miss rate from the L1 102 . Therefore there is an L2 104 is required. Note that most of what is called a “core” 100 is actually memory. When multiple cores 100 are aggregated into a single “multi-core chip” 105 , the chip is large, but most of it is memory.
- FIG. 2 illustrates today's prior art technology for multi-core chips.
- the multi-core chip 105 is mounted on a Dual-Chip Module (DCM) 200 , which can either be ceramic or organic, where it is connected to another chip shown as L3 201 .
- DCM Dual-Chip Module
- L3 201 usually contains not only another layer of cache, but also other functions that facilitate the operation of the nest (not shown) (i.e. all system functions excluding the processor, cache, and memory; such as external memory, I/O controllers, wiring, PC boards, etc.), and functions that connect the DCM 200 to other devices in the system.
- DCMs 200 are mounted with another layer of packaging 202 (and/or other interconnection means), as shown.
- packaging 202 and/or other interconnection means
- the four 4-core chips could be put together on a 4-chip module (not shown), and connected to other layers of cache put off module.
- a 64-way system can be made out of four 16-way systems 203 (e.g. probably four boards in a chassis); a 256-way system by placing four chassis into a frame; multiple frames in a room, etc.
- SOP Systems On Package
- SC Silicon Carrier
- the wiring on the silicon wafer henceforth called a Silicon Carrier (SC)
- SC Silicon Carrier
- a “chip-to-chip” electrical signal that propagates across a SC appears to be very much the same as any other electrical signal propagating across a single, larger chip at a similar distance.
- the SC is purely a wiring vehicle and not subject to the blockages encountered on a normal chip, wiring can be shielded much more easily, resulting in better electrical characteristics.
- SC technology appears to offer many advantages. It allows several chips to be connected together to operate as a single, larger chip.
- the resulting chip system is larger than the theoretical size of any real chip, but because the chip is partitioned into smaller pieces, the effective yield is higher.
- the system of FIG. 2 can be implemented more efficiently and much denser.
- the advantage of making this denser is that more processors and cache can be aggregated into a subsystem, which allows a larger system (in number of processors) to be implemented in a given volume. Further, operation at much reduced power is possible using this densely integrated solution compared to no integration with chip stacks and silicon carrier due to power savings such as voltage reduction, reduced RC (because of reduced line length, size in chip stacks, and between chips on a silicon carrier), and lower noise.
- FIG. 3 depicts two ways in which we could make a 16-way system 301 , 302 using the 4-core chips 105 of FIG. 1 and some L3 chips 201 . Shown in the top left corner, four of these 4-way chips 105 are assembled together on a large SC to make a 16-way chip 300 . To make a system, the 16-way SC “chip” 300 is combined with some L3 chips 201 using standard packaging as shown on the right 301 . Alternately, four of the 4-way chips 105 are combined with L3 chips 201 on a huge SC 302 to implement the entire system in one step.
- This later implementation 302 requires fewer levels of packaging, has shorter wires (hence lower power—and perhaps wider paths) between the elements, and it results in a smaller footprint.
- the SC is much larger in 302 , and the power density is higher. Which of these implementations ( 301 or 302 ) is “better” depends on the characteristic being optimized. At this level of abstraction, it is impossible to say which of these is cheaper by the time that the entire system is put together.
- 3D and SC seem to offer many of the same advantages.
- Each technology enables multiple chips to be integrated into a larger, monolithic entity, appearing as if it were a much larger chip.
- circuits on the component chips can be arranged such that most of the required interconnections between them are directly over (or under) each other, then the interconnection wiring is much shorter than for SC.
- Most logic circuitry cannot generally be arranged in this way, however this arrangement can work well for memory circuits.
- 11/453,885 entitled “METHOD FOR ACHIEVING VERY HIGH BANDWIDTH BETWEEN THE LEVELS OF A CACHE HIERARCHY IN 3-DIMENSIONAL STRUCTURES, AND A 3-DIMENSIONAL STRUCTURE RESULTING THEREFROM,” filed on Jun. 16, 2006, teaches one method of constructing a cache hierarchy be leveraging 3D technology that offers unprecedented amounts of bandwidth between the layers at very low power, which is hereby incorporated by reference in its entirety.
- FIG. 4 illustrates a system built using 3D stack technology only, as described in U.S. patent application Ser. No. 11/453,885, which is hereby incorporated by reference in its entirety. That prior art capitalizes on the enormous bandwidth that 3D offers in going between the levels of a cache hierarchy if the bits within the respective caches were placed according to a certain method. Therefore, to take advantage of that bandwidth opportunity, that prior art split out the L1.5s 103 and L2s 104 as separate chips that stacked on top of each other.
- the L2s 104 are removed, and a new chip 401 is assembled comprising only processors 101 and L1.5s 103 covering the same area as the prior 4-core component 105 .
- the new chip 401 contains twelve cores 101 with their corresponding L1.5s 103 .
- Assembling layers of L2s 102 and L3s 201 into new chips 402 having the same footprint as the new twelve-core chip 401 , create a cache hierarchy. Then these chips 401 and 402 are stacked up to make a twelve-core system 403 .
- a computer chip structure and computer system have at least one single-layered chip, at least one multi-layered chip stack, and a carrier package, characterized by electrical interconnections of less than 100 microns diameter, where the single-layered chip and the multi-layered chip stack are each electrically coupled to the electrical interconnections of the carrier package, and the single-layered chip is communicatively coupled to the multi-layered chip stack through the carrier package so that an electrical signal propagates over a given distance between the single-layered chip and the multi-layered chip stack at substantially a speed of propagation for a single layer chip over the given distance.
- the single-layered chip is a processor, having single or multiple cores
- the multi-layered chip is a memory cache stack.
- At least one of the single-layered chip and the multi-layered chip stack is electrically coupled to the carrier package by interconnect vias.
- the interconnect vias have a density that is as least as great as two thousand five hundred interconnections per square centimeter (2500 interconnections/cm 2 ).
- the carrier package also contains a plurality of integrated decoupling capacitors, each coupling capacitor physically positioned directly under an interconnect via on the side of the carrier package opposite the side the single-layered chip and the multi-layered chip stack are electrically coupled thereto.
- Power is delivered to the single-layered chip by means of integrated decoupling capacitors located directly under an interconnect via of the single-layered chip, and delivered to the multi-layered chip stack by means of integrated decoupling capacitors located directly under an interconnect via of the multi-layered chip stack.
- the interconnect vias are created by means of silicon through vias, electrical interconnections, thermal vias, thermal interconnections, or thermal interface materials.
- the carrier package is made of silicon, organic materials with build up layers, organic materials without build up layers, organic materials with fiber reinforcement, or organic materials without fiber reinforcement.
- the carrier package has a first surface plane and a second surface plane opposing the first surface plane, and the single-layered chip and the multi-layered chip stack are physically positioned on the same surface plane of the carrier package.
- the computer chip structure has a first cooling structure thermally coupled to a top-side of the single-layered chip, and a second cooling structure thermally coupled to a bottom-side of the multi-layered chip stack, providing at least two independent thermal paths. Each thermal path is created by means of at least one of electrical vias, electrical interconnections, thermal vias, thermal interconnections, and thermal interface materials.
- the carrier package has a first surface plane and a second surface plane opposing the first surface plane, and the single-layered chip and the multi-layered chip stack are physically positioned on opposing surface planes of the carrier package such that horizontal wiring distances in intra-level busses are minimized.
- the computer chip structure contains a second carrier package electrically coupled to at least one multi-layered chip stack by interconnect vias.
- the second carrier package is thermally coupled to the multi-layered chip stack for providing a second, independent path for heat dissipation.
- the computer chip structure contains a plurality of multi-layered chip stacks and a carrier package characterized by electrical interconnections of less than 100 microns diameter, wherein the multi-layered chip stacks are each electrically coupled to the electrical interconnections of the carrier package, and communicatively coupled to at least one other multi-layered chip stack through the carrier package so that an electrical signal propagates over a given distance between the multi-layered chip stacks at substantially a speed of propagation for a single layer chip over the given distance.
- FIG. 1 is a block diagram illustrating a prior art single core with its cache hierarchy, and a prior art multi-core chip.
- FIG. 2 is a block diagram illustrating a prior art dual-chip module using the multi-core chip of FIG. 1 , and a prior art 16-processor system made from dual-chip modules.
- FIG. 3 is a block diagram illustrating a prior art 16-way multi-chip on a Silicon Carrier (SC) and two possible prior-art systems that can be made either with the SC and a second-level package, or with a huge SC alone.
- SC Silicon Carrier
- FIG. 4 is a block diagram illustrating a prior art 12-way processor system with a cache hierarchy made on the same footprint of a multi-core chip using 3D technology.
- FIG. 5 is a block diagram illustrating an exemplary 24-way single-socket processor system in accordance with one embodiment of the present invention using a combination of both SC and 3D technologies.
- FIG. 6 is a block diagram illustrating an exemplary 24-way processor system having enormous caches contained in multiple, vertical towers, by partitioning the system in accordance with one embodiment of the present invention.
- FIG. 7 is a block diagram highlighting the simplicity of an exemplary system board when the multiprocessor is socketed in a manner set forth by an embodiment of the present invention.
- FIG. 8 is a block diagram illustrating an exemplary 24-way single-socket processor system in accordance with another embodiment of the present invention using a combination of both SC and 3D technologies.
- FIG. 9 is a more detailed block diagram of the 24-way single-socket processor system of FIG. 5 , illustrating exemplary cooling techniques in accordance with an embodiment of the present invention.
- the terms “a” or “an,” as used herein, are defined as “one or more than one.”
- the term “plurality,” as used herein, is defined as “two or more than two.”
- the term “another,” as used herein, is defined as “at least a second or more.”
- the terms “including” and/or “having,” as used herein, are defined as “comprising” (i.e., open language).
- the term “coupled,” as used herein, is defined as “connected, although not necessarily directly, and not necessarily mechanically.”
- the terms “controls,” “button,” “knob,” and “switch” are used interchangeably to indicate a mechanical means for a user to control functions of a piece of equipment instrument or device.
- program is defined as “a sequence of instructions designed for execution on a computer system.”
- a program, computer program, or software application typically includes a subroutine, a function, a procedure, an object method, an object implementation, an executable application, an applet, a servlet, a source code, an object code, a shared library/dynamic load library and/or other sequence of instructions designed for execution on a computer system.
- the present invention overcomes problems with the prior art by positioning a new system structure that combines 3D and SC technologies as mutually synergistic technologies instead of viewing these technologies as mutually competing technologies.
- the strengths of each technology are used to compensate for the other's weakness. In this way, a system is constructed that is far beyond the scale of what could be done with either technology by itself
- An embodiment of the present invention offers two major improvements over the prior art. First, all cache levels that are typically located outside the processor (i.e. all cache levels greater than L1) are removed from the processor chip. This allows the logic chip containing the cores to be more logically dense than ever before realized.
- processors logic circuits
- caches lack the simple redundancy possible with memories, resulting in low-yield problems.
- the combination of processors and memory increases the risk associated with production yield and therefore makes the system costly. By removing all of the cache, the entire area of the chip is consumed exclusively by cores. This lowers yield loss because redundancy is accomplished by the simple addition of a few extra cores without adding all of the area that their caches would have required.
- a second improvement over prior art is that neither the power density nor the thermal resistance is increased to the hottest component—the processor chip. This allows the cores to operate in a higher power regime, if desired, achieving a higher performance by providing area array power feeds to the processor and area array cooling to the opposite side of the processor chip without the need to remove heat from the processor chip, through other chips in a stack, to a heat sink.
- the logic density is increased significantly by segregating the core processors 101 and level L1.5 memory cache 103 from higher cache levels in the hierarchy.
- the resulting 12-core chip 401 is designed to share an identical footprint as each layer of cache memory 102 , 201 to enable vertical stacking of layers.
- FIG. 5 An exemplary embodiment of the present invention, shown in FIG. 5 , builds on this concept by further removing the L1.5 memories 103 from the 12-core chip 401 , and filling in the area vacated by the L1.5s 103 with additional cores 101 . This results in a 24-core all-logic chip 501 , which has the same area as the original 12-core chip 401 . Next, a new chip layer 502 is created containing only L1.5 memory 103 .
- Additional L2 104 and L3 201 chips are assembled using complementary 3D & SC technologies.
- a 3D stack 503 of all of the memory caches (L1.5, L2, and L3) is produced and mounted adjacent to the 24-core logic chip 501 on a carrier package 504 .
- Interconnections connecting the component chips 501 , 503 to the package 504 have a pitch less than 100 microns, meaning an interconnect density of greater than two thousand five hundred interconnects per square centimeter (2500/cm 2 ).
- the data bus between the 24-core layer 502 and the cache stack 503 is routed through the carrier package 504 . This results in a single socket 24-way complete system 505 .
- FIG. 6 illustrates one manner in which multiple cache stacks 601 are positioned.
- the 24-core logic chip 501 is located in the center of the carrier package 602 , with four cache stacks 601 positioned around it.
- each cache stack 601 serves just six of the twenty-four processors 101 . If each of these cache stacks 601 has a footprint comparable to the original chip stack 503 , then the L1.5s 502 can be much bigger, since the footprint of the chip need only accommodate six of them.
- the electrical signal actually propagates over a given distance between the multi-core processor and the multi-layered memory cache stack at substantially a speed of propagation for a single layer chip over the given distance. (At this point, it should be noted that the processor chip 501 and cache stacks 601 , as depicted in FIG.
- each cache stack 601 are not drawn to scale, but merely enhanced to illustrate a concept of the present invention.
- the layers of each cache stack 601 are actually thinned down to a point where the height of the resulting cache stacks 601 are equivalent to the height of the processor chip 501 for easy manufacturability.
- the cache stack is the entire hierarchy beyond the L1, with some horizontal wiring required across the SC to reach the L1.5, it should be understood that this need not be the exclusive manner of partitioning. For example, if the power density of the processor chip is not unwieldy, the L1.5 layer 502 is stacked upon the processor chip 501 , and the cache towers 503 begin with the L2 level.
- FIG. 6 A highly desirable feature of FIG. 6 is that additional cache capacity is accomplished in three ways. First, since there are four cache towers 601 , instead of the single tower 503 shown in FIG. 5 , the cache capacity is at least quadrupled. Second, since the hottest component—the processors 101 —have been removed from the towers 601 , the stacks are able to be stacked higher because there is less power density. Thus, the capacity is further increased by factor of two or more from the increased stack height. Third, it should be noticed that in FIG. 6 , the four corners of the SC 602 are empty. Additional towers 601 can be placed in the corners of the SC 602 (e.g., doubling the amount of cache), or other functions, such as I/O channels, optical transceivers, or any other desired functions can be located in these corners.
- a single socket system built using SC and 3D in conjunction, has many more processors and much more cache memory than could be put together otherwise. More surprisingly, while the total power consumption of all of the added processors and cache is greater because of the increased number of integrated components, the power density is less than that of the smaller capacity prior-art system when partitioned in the manner set forth above. This is accomplished by physically isolating the high-powered processors from lower-powered memory components. The low-powered memory stacks (SRAM and DRAM) are then multiplied and built even higher than before possible. The connections between the processors and the cache towers are very broad, enabling an extraordinarily powerful socket with a reasonably small footprint.
- a 24-processor 6 is placed onto a single board 700 .
- the 24-way system 600 of FIG. 6 appears as a single component 600 on the board 700 .
- the only other components on this board 600 is the memory system 701 , comprising only a couple of columns of DIMMs 701 . Since there is only a single component 600 (besides the DIMMs) on the board 700 , the board wiring should be extremely simple, and the board itself cheap.
- FIG. 8 illustrates another embodiment of the present invention using Package-on-Package techniques for vertical 3D integration.
- a 24-core logic chip 501 containing only the processor cores 101 and L1 memory 103 is assembled in the same manner as shown in FIG. 5 .
- the 24-core logic chip 501 is then mounted on its own silicon carrier 801 .
- the memory cache 503 is combined with the L1.5 memory layer 502 using 3D technology and is sandwiched between the silicon carrier 801 carrying the 24-core logic chip 501 , and an additional carrier 802 for routing purposes.
- integrated decoupling capacitors 803 are located directly underneath each chip or chip stack and are connected using the interconnects.
- integrated decoupling capacitors 803 provide decoupling by means of a low inductance path, which provides advantages such as, but not limited to, reduced noise, lower voltage circuit operation, improved voltage distribution (i.e. lower voltage droop), higher frequency operation, and any combination thereof.
- the lower carrier package 802 can be made from a variety of materials, including ceramics, silicon, and organic materials such as organic packages with build up layers, without build up layers, with fiber reinforcement, without fiber reinforcement.
- power delivery to the chip 501 and chip stacks 502 , 503 is provided through the package 802 with the added benefit of integrated decoupling capacitors 803 in some applications, as described above.
- the present invention provides a significant advantage over the prior art, in terms of power delivery, by keeping the processor 501 separate from the cache chip stack 502 , 503 , thereby reducing the number of power delivery connections needed through the silicon processor 501 and cache chip stacks 502 , 503 . This additional area would have previously detracted from the area available in both the processor 501 and cache chip stacks 502 , 503 for active circuits and for signal and power wiring.
- the present invention offers an additional advantage over the prior 3D technology because there are now separate, multiple independent paths for cooling both the processor chip 501 and the cache chip stack 502 , 503 . Because the processor chip 501 is no longer vertically mounted to the cache stack 502 , 503 , cooling is provided on both the topsides and the backsides of the processor chip 501 and of the cache stack 502 , 503 . In addition, the cooling of the chip stack 502 , 503 is engineered to utilize vertical thermal interconnections 805 between the cache chips in the cache chip stack 502 , 503 .
- the thermal path is comprised of electrical interconnections, thermal vias, thermal spreaders and/or thermal interconnections.
- the thermal connections 902 benefit from added Metal vias such as copper vias and metal interconnections between chips in a chip stack.
- Thermal interconnections include the use of additional mechanical and thermal connections such as added pads, solder connections, thermal interface materials such as filled adhesives or alternate means. Further cooling is enhanced using a wide range of assembled module options such as heat spreaders, heat sinks, heat pipes, heat fins, air cooling, liquid cooling such as but not limited to microchannel cooling or combinations of cooling methods and structures used in the industry at a module level.
- cooling hat 901 at the topside of the processor chip 501 and another at the bottom of the chip stack 503 by means of a heat sink and thermal connections at the bottom side of the cache stack 503 to the package 504 .
- the spreader 802 would also serve as a package 802 for power, electrical and mechanical integrity.
- Another example shows one traditional cooling surface 901 placed at the at top of processor layer 501 , and the second carrier package 801 placed at the bottom of the cache stack 503 , as shown in FIG. 9 .
- the multiple cooling paths allow for more efficient cooling than can be realized using only 3D technology.
- the prior-art subsystems of FIGS. 2 and 3 would have taken a very large, complicated board, or even multiple boards, to implement a 24-way system. In those cases, the complexity level may have limited the system to a maximum 16-way system.
- the present invention enables a simpler physical system. Not only is the new system a higher capacity system (in number of processors), but it is more power efficient because it has much shorter busses; more performance efficient because the busses can be wider; more cost efficient because redundancy in the cores enables lower yield loss; and capable of having a lower power density.
- the circuit as described above is part of the design for an integrated circuit chip.
- the chip design is created in a graphical computer programming language, and stored in a computer storage medium (such as a disk, tape, physical hard drive, or virtual hard drive such as in a storage access network). If the designer does not fabricate chips or the photolithographic masks used to fabricate chips, the designer transmits the resulting design by physical means (e.g., by providing a copy of the storage medium storing the design) or electronically (e.g., through the Internet) to such entities, directly or indirectly.
- the stored design is then converted into the appropriate format (e.g., GDSII) for the fabrication of photolithographic masks, which typically include multiple copies of the chip design in question that are to be formed on a wafer.
- the photolithographic masks are utilized to define areas of the wafer (and/or the layers thereon) to be etched or otherwise processed.
- the method as described above is used in the fabrication of integrated circuit chips.
- the resulting integrated circuit chips can be distributed by the fabricator in raw wafer form (that is, as a single wafer that has multiple unpackaged chips), as a bare chip, or in a packaged form.
- the chip is mounted in a single chip package (such as a plastic carrier, with leads that are affixed to a motherboard or other higher level carrier) or in a multi-chip package (such as a ceramic carrier that has either or both surface interconnections or buried interconnections).
- the chip is then integrated with other chips, discrete circuit elements, and/or other signal processing devices as part of either (a) an intermediate product, such as a motherboard, or (b) an end product.
- the end product can be any product that includes integrated circuit chips, ranging from toys and other low-end applications to advanced computer products having a display, a keyboard, or other input device, and a central processor.
- a computer system may include, inter alia, one or more computers and at least a computer readable medium, allowing a computer system, to read data, instructions, messages or message packets, and other computer readable information from the computer readable medium.
- the computer readable medium may include non-volatile memory, such as ROM, Flash memory, Disk drive memory, CD-ROM, and other permanent storage. Additionally, a computer readable medium may include, for example, volatile storage such as RAM, buffers, cache memory, and network circuits. Furthermore, the computer readable medium may comprise computer readable information in a transitory state medium such as a network link and/or a network interface, including a wired network or a wireless network that allow a computer system to read such computer readable information.
Abstract
Description
-
- 1. A complete 12-way system now has the same footprint as the old 4-way chip, which is just a subsystem. That is, the single-socket 12-way system does not require any more intermediate packaging layers.
- 2. Depending on the number of chips stacked, there is a potential for including considerably more cache than would have had the area for in standard packaging.
- 3. The busses between the levels of the cache hierarchy can be extremely wide, and extremely short, offering unprecedented amounts of bandwidth at low power.
-
- 1. The total capacity of the cache is limited by the amount of layer that can reasonably be stacked in the chips.
- 2. There is a potential for a greater power density than can dispensed using conventional cooling.
- 3. The thermal resistance is increased when the stacks are high, further complicating the cooling.
- 4. Every layer must be designed and built for the entire chip stack to function, leading to longer development times and costs for mask levels and integration.
-
- 1. In the case that circuitry is arranged such that the required interconnections are directly “over and under” each other, the resulting busses in 3D will be on the scale of a millimeter (i.e. principally be in the vertical stack), hence they can be very fast and relatively low power. In SC, the same busses will be on the scale of a centimeter, and will not be as fast or as efficient.
- 2. With SC, all of the chips that are to be interconnected must be arranged in a plane. Therefore, if there are many chips (such as with memory systems), the footprint of the aggregations will be very large. This can be a very inefficient use of space on the next-level package. Further, there are limits to how large the SC can be made in a cost-effective way. Thus, only the number of component chips that fit within that limit can reasonably be integrated.
- 3. In 3D, when more than a few planes are piled up into a stack, the total power density can become too high and lead to challenges both with power delivery into the stack and cooling of all chips in the stack, especially if using low cost standard cooling methods. Concurrently, the thermal resistance grows with the stack height, compounding this problem. This is particularly problematic when the entire system—including processors—is in the stack where often a processor may be a high power density chip and require significant cooling for many applications.
Claims (18)
Priority Applications (4)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
US11/538,567 US7518225B2 (en) | 2006-06-16 | 2006-10-04 | Chip system architecture for performance enhancement, power reduction and cost reduction |
PCT/US2007/071370 WO2008100324A2 (en) | 2006-06-16 | 2007-06-15 | Method for achieving very high bandwidth between the levels of a cache hierarchy in 3-dimensional structures, and a 3- dimensional structure resulting therefrom |
CN2007800188856A CN101473436B (en) | 2006-06-16 | 2007-06-15 | Method for achieving very high bandwidth between the levels of a cache hierarchy in 3-dimensional structures, and a 3-dimensional structure resulting therefrom |
EP07863368A EP2036126A2 (en) | 2006-06-16 | 2007-06-15 | Method for achieving very high bandwidth between the levels of a cache hierarchy in 3-dimensional structures, and a 3-dimensional structure resulting therefrom |
Applications Claiming Priority (2)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
US11/453,885 US7616470B2 (en) | 2006-06-16 | 2006-06-16 | Method for achieving very high bandwidth between the levels of a cache hierarchy in 3-dimensional structures, and a 3-dimensional structure resulting therefrom |
US11/538,567 US7518225B2 (en) | 2006-06-16 | 2006-10-04 | Chip system architecture for performance enhancement, power reduction and cost reduction |
Related Parent Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
US11/453,885 Continuation-In-Part US7616470B2 (en) | 2006-06-16 | 2006-06-16 | Method for achieving very high bandwidth between the levels of a cache hierarchy in 3-dimensional structures, and a 3-dimensional structure resulting therefrom |
Publications (2)
Publication Number | Publication Date |
---|---|
US20070290315A1 US20070290315A1 (en) | 2007-12-20 |
US7518225B2 true US7518225B2 (en) | 2009-04-14 |
Family
ID=38860723
Family Applications (3)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
US11/453,885 Expired - Fee Related US7616470B2 (en) | 2006-06-16 | 2006-06-16 | Method for achieving very high bandwidth between the levels of a cache hierarchy in 3-dimensional structures, and a 3-dimensional structure resulting therefrom |
US11/538,567 Active 2027-02-03 US7518225B2 (en) | 2006-06-16 | 2006-10-04 | Chip system architecture for performance enhancement, power reduction and cost reduction |
US12/116,771 Expired - Fee Related US7986543B2 (en) | 2006-06-16 | 2008-05-07 | Method for achieving very high bandwidth between the levels of a cache hierarchy in 3-dimensional structures, and a 3-dimensional structure resulting therefrom |
Family Applications Before (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
US11/453,885 Expired - Fee Related US7616470B2 (en) | 2006-06-16 | 2006-06-16 | Method for achieving very high bandwidth between the levels of a cache hierarchy in 3-dimensional structures, and a 3-dimensional structure resulting therefrom |
Family Applications After (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
US12/116,771 Expired - Fee Related US7986543B2 (en) | 2006-06-16 | 2008-05-07 | Method for achieving very high bandwidth between the levels of a cache hierarchy in 3-dimensional structures, and a 3-dimensional structure resulting therefrom |
Country Status (4)
Country | Link |
---|---|
US (3) | US7616470B2 (en) |
EP (1) | EP2036126A2 (en) |
CN (1) | CN101473436B (en) |
WO (1) | WO2008100324A2 (en) |
Cited By (9)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20080150088A1 (en) * | 2006-12-20 | 2008-06-26 | Reed Paul A | Method for incorporating existing silicon die into 3d integrated stack |
US20100288544A1 (en) * | 2005-12-27 | 2010-11-18 | Ibiden Co., Ltd | Multilayer printed wiring board |
US20110119508A1 (en) * | 2009-11-16 | 2011-05-19 | International Business Machines Corporation | Power Efficient Stack of Multicore Microprocessors |
US8163642B1 (en) * | 2005-08-10 | 2012-04-24 | Altera Corporation | Package substrate with dual material build-up layers |
US20120170345A1 (en) * | 2011-01-04 | 2012-07-05 | Choi Jang Seok | Stacked semiconductor device and method of manufacturing the same |
US8299608B2 (en) | 2010-07-08 | 2012-10-30 | International Business Machines Corporation | Enhanced thermal management of 3-D stacked die packaging |
US8466543B2 (en) | 2010-05-27 | 2013-06-18 | International Business Machines Corporation | Three dimensional stacked package structure |
US8569874B2 (en) | 2011-03-09 | 2013-10-29 | International Business Machines Corporation | High memory density, high input/output bandwidth logic-memory structure and architecture |
CN107564881A (en) * | 2017-08-29 | 2018-01-09 | 睿力集成电路有限公司 | A kind of chip stack stereo encapsulation structure and its manufacture method |
Families Citing this family (23)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US8032711B2 (en) * | 2006-12-22 | 2011-10-04 | Intel Corporation | Prefetching from dynamic random access memory to a static random access memory |
US20080237738A1 (en) * | 2007-03-27 | 2008-10-02 | Christoph Andreas Kleint | Integrated circuit, cell, cell arrangement, method for manufacturing an integrated circuit, method for manufacturing a cell arrangement; memory module |
US9229887B2 (en) * | 2008-02-19 | 2016-01-05 | Micron Technology, Inc. | Memory device with network on chip methods, apparatus, and systems |
US7978721B2 (en) | 2008-07-02 | 2011-07-12 | Micron Technology Inc. | Multi-serial interface stacked-die memory architecture |
US8086913B2 (en) | 2008-09-11 | 2011-12-27 | Micron Technology, Inc. | Methods, apparatus, and systems to repair memory |
US20100078788A1 (en) | 2008-09-26 | 2010-04-01 | Amir Wagiman | Package-on-package assembly and method |
JP2010108204A (en) * | 2008-10-30 | 2010-05-13 | Hitachi Ltd | Multichip processor |
US9123552B2 (en) | 2010-03-30 | 2015-09-01 | Micron Technology, Inc. | Apparatuses enabling concurrent communication between an interface die and a plurality of dice stacks, interleaved conductive paths in stacked devices, and methods for forming and operating the same |
CN104094402A (en) | 2011-12-01 | 2014-10-08 | 考文森智财管理公司 | CPU with stacked memory |
CN102662909B (en) * | 2012-03-22 | 2013-12-25 | 东华理工大学 | Three-dimensional many-core system on chip |
US8891279B2 (en) | 2012-09-17 | 2014-11-18 | International Business Machines Corporation | Enhanced wiring structure for a cache supporting auxiliary data output |
US9378793B2 (en) * | 2012-12-20 | 2016-06-28 | Qualcomm Incorporated | Integrated MRAM module |
US9037791B2 (en) | 2013-01-22 | 2015-05-19 | International Business Machines Corporation | Tiered caching and migration in differing granularities |
US9336144B2 (en) * | 2013-07-25 | 2016-05-10 | Globalfoundries Inc. | Three-dimensional processing system having multiple caches that can be partitioned, conjoined, and managed according to more than one set of rules and/or configurations |
CN107564825B (en) * | 2017-08-29 | 2018-09-21 | 睿力集成电路有限公司 | A kind of chip double-side encapsulating structure and its manufacturing method |
FR3082656B1 (en) | 2018-06-18 | 2022-02-04 | Commissariat Energie Atomique | INTEGRATED CIRCUIT COMPRISING MACROS AND ITS MANUFACTURING METHOD |
CN110540164A (en) * | 2019-10-09 | 2019-12-06 | 太仓全众智能装备有限公司 | Bottle type buffer memory machine |
EP4071593A4 (en) * | 2021-02-26 | 2023-08-23 | Beijing Vcore Technology Co.,Ltd. | Stacked cache system based on sedram, and control method and cache device |
CN113097383B (en) * | 2021-03-09 | 2023-07-18 | 长江先进存储产业创新中心有限责任公司 | CPU and manufacturing method thereof |
CN113096706B (en) * | 2021-03-09 | 2023-06-16 | 长江先进存储产业创新中心有限责任公司 | CPU and manufacturing method thereof |
US11887908B2 (en) | 2021-12-21 | 2024-01-30 | International Business Machines Corporation | Electronic package structure with offset stacked chips and top and bottom side cooling lid |
CN114244920B (en) * | 2021-12-29 | 2024-02-09 | 苏州盛科通信股份有限公司 | New and old chip stacking head compatible method and system and chip |
WO2023203435A1 (en) * | 2022-04-22 | 2023-10-26 | 株式会社半導体エネルギー研究所 | Semiconductor device |
Citations (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US5702984A (en) * | 1993-09-13 | 1997-12-30 | International Business Machines Corporation | Integrated mulitchip memory module, structure and fabrication |
US7217994B2 (en) * | 2004-12-01 | 2007-05-15 | Kyocera Wireless Corp. | Stack package for high density integrated circuits |
Family Cites Families (11)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US5133061A (en) * | 1987-10-29 | 1992-07-21 | International Business Machines Corporation | Mechanism for improving the randomization of cache accesses utilizing abit-matrix multiplication permutation of cache addresses |
US6059835A (en) * | 1997-06-13 | 2000-05-09 | International Business Machines Corporation | Performance evaluation of processor operation using trace pre-processing |
US6175160B1 (en) * | 1999-01-08 | 2001-01-16 | Intel Corporation | Flip-chip having an on-chip cache memory |
US6725334B2 (en) * | 2000-06-09 | 2004-04-20 | Hewlett-Packard Development Company, L.P. | Method and system for exclusive two-level caching in a chip-multiprocessor |
US6678814B2 (en) * | 2001-06-29 | 2004-01-13 | International Business Machines Corporation | Method and apparatus for allocating data usages within an embedded dynamic random access memory device |
JP4047788B2 (en) * | 2003-10-16 | 2008-02-13 | 松下電器産業株式会社 | Compiler device and linker device |
US7130967B2 (en) * | 2003-12-10 | 2006-10-31 | International Business Machines Corporation | Method and system for supplier-based memory speculation in a memory subsystem of a data processing system |
US7305523B2 (en) * | 2005-02-12 | 2007-12-04 | International Business Machines Corporation | Cache memory direct intervention |
US7533321B2 (en) * | 2005-09-13 | 2009-05-12 | International Business Machines Corporation | Fault tolerant encoding of directory states for stuck bits |
US7404041B2 (en) * | 2006-02-10 | 2008-07-22 | International Business Machines Corporation | Low complexity speculative multithreading system based on unmodified microprocessor core |
JP4208895B2 (en) * | 2006-05-30 | 2009-01-14 | 株式会社東芝 | Cache memory device and processing method |
-
2006
- 2006-06-16 US US11/453,885 patent/US7616470B2/en not_active Expired - Fee Related
- 2006-10-04 US US11/538,567 patent/US7518225B2/en active Active
-
2007
- 2007-06-15 EP EP07863368A patent/EP2036126A2/en not_active Withdrawn
- 2007-06-15 CN CN2007800188856A patent/CN101473436B/en not_active Expired - Fee Related
- 2007-06-15 WO PCT/US2007/071370 patent/WO2008100324A2/en active Application Filing
-
2008
- 2008-05-07 US US12/116,771 patent/US7986543B2/en not_active Expired - Fee Related
Patent Citations (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US5702984A (en) * | 1993-09-13 | 1997-12-30 | International Business Machines Corporation | Integrated mulitchip memory module, structure and fabrication |
US7217994B2 (en) * | 2004-12-01 | 2007-05-15 | Kyocera Wireless Corp. | Stack package for high density integrated circuits |
Cited By (14)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US8163642B1 (en) * | 2005-08-10 | 2012-04-24 | Altera Corporation | Package substrate with dual material build-up layers |
US8334466B2 (en) * | 2005-12-27 | 2012-12-18 | Ibiden Co., Ltd. | Multilayer printed wiring board |
US20100288544A1 (en) * | 2005-12-27 | 2010-11-18 | Ibiden Co., Ltd | Multilayer printed wiring board |
US8110899B2 (en) * | 2006-12-20 | 2012-02-07 | Intel Corporation | Method for incorporating existing silicon die into 3D integrated stack |
US20080150088A1 (en) * | 2006-12-20 | 2008-06-26 | Reed Paul A | Method for incorporating existing silicon die into 3d integrated stack |
US20110119508A1 (en) * | 2009-11-16 | 2011-05-19 | International Business Machines Corporation | Power Efficient Stack of Multicore Microprocessors |
US8417974B2 (en) | 2009-11-16 | 2013-04-09 | International Business Machines Corporation | Power efficient stack of multicore microprocessors |
US8466543B2 (en) | 2010-05-27 | 2013-06-18 | International Business Machines Corporation | Three dimensional stacked package structure |
US8299608B2 (en) | 2010-07-08 | 2012-10-30 | International Business Machines Corporation | Enhanced thermal management of 3-D stacked die packaging |
US20120170345A1 (en) * | 2011-01-04 | 2012-07-05 | Choi Jang Seok | Stacked semiconductor device and method of manufacturing the same |
US9183890B2 (en) * | 2011-01-04 | 2015-11-10 | Samsung Electronics Co., Ltd. | Stacked semiconductor device and method of manufacturing the same |
US8569874B2 (en) | 2011-03-09 | 2013-10-29 | International Business Machines Corporation | High memory density, high input/output bandwidth logic-memory structure and architecture |
CN107564881A (en) * | 2017-08-29 | 2018-01-09 | 睿力集成电路有限公司 | A kind of chip stack stereo encapsulation structure and its manufacture method |
CN107564881B (en) * | 2017-08-29 | 2018-09-21 | 睿力集成电路有限公司 | A kind of chip stack stereo encapsulation structure and its manufacturing method |
Also Published As
Publication number | Publication date |
---|---|
WO2008100324A9 (en) | 2009-05-22 |
US7986543B2 (en) | 2011-07-26 |
EP2036126A2 (en) | 2009-03-18 |
WO2008100324A2 (en) | 2008-08-21 |
US20070290315A1 (en) | 2007-12-20 |
US20070294479A1 (en) | 2007-12-20 |
US20080209126A1 (en) | 2008-08-28 |
US7616470B2 (en) | 2009-11-10 |
WO2008100324A3 (en) | 2011-01-13 |
CN101473436B (en) | 2011-04-13 |
CN101473436A (en) | 2009-07-01 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
US7518225B2 (en) | Chip system architecture for performance enhancement, power reduction and cost reduction | |
US11693801B2 (en) | Stacked semiconductor device assembly in computer system | |
US8445918B2 (en) | Thermal enhancement for multi-layer semiconductor stacks | |
US7611924B2 (en) | Integrated circuit package with chip-side signal connections | |
US9495498B2 (en) | Universal inter-layer interconnect for multi-layer semiconductor stacks | |
US7279795B2 (en) | Stacked die semiconductor package | |
US8710676B2 (en) | Stacked structure and stacked method for three-dimensional chip | |
RU2419179C2 (en) | Integrated circuit device and method of making said device | |
KR20140109914A (en) | Cpu with stacked memory | |
US10090236B2 (en) | Interposer having a pattern of sites for mounting chiplets | |
KR20130015461A (en) | Semiconductor stack package and the method for manufacturing the same | |
Clermidy et al. | 3D embedded multi-core: Some perspectives | |
US20120049361A1 (en) | Semiconductor integrated circuit | |
US11824046B2 (en) | Symbiotic network on layers | |
CN113574662A (en) | Interposer, microelectronic device assembly including the same, and method of manufacture | |
JP2009135204A (en) | System-in-package | |
US6949826B2 (en) | High density semiconductor package | |
KR101153222B1 (en) | Stacked chip package, semiconductor module including the same and method of manufacturing stacked chip package | |
England et al. | Advanced Packaging Drivers/Opportunities to Support Emerging Artificial Intelligence Applications | |
US20220214972A1 (en) | Integrated Circuit with 3D Partitioning | |
US20120175763A1 (en) | Integrated circuit packaging including auxiliary circuitry | |
US20230197705A1 (en) | Interconnection structures for high-bandwidth data transfer | |
EP0698294A1 (en) | Logical three-dimensional interconnections between integrated circuit chips using a two-dimensional multi-chip module package | |
WO2022068467A1 (en) | Encapsulation structure, apparatus, board card, and method for laying out integrated circuit | |
KR101104380B1 (en) | Semiconductor chip package, semiconductor module including semiconductor chip package, electronic system including semiconductor module and method of manufacturing semiconductor chip package |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
AS | Assignment |
Owner name: INTERNATIONAL BUSINESS MACHINES CORPORATION, NEW Y Free format text: ASSIGNMENT OF ASSIGNORS INTEREST;ASSIGNORS:EMMA, PHILIP G.;KNICKERBOCKER, JOHN U.;PATEL, CHIRAG S.;REEL/FRAME:018347/0155;SIGNING DATES FROM 20060926 TO 20061003 |
|
FEPP | Fee payment procedure |
Free format text: PAYOR NUMBER ASSIGNED (ORIGINAL EVENT CODE: ASPN); ENTITY STATUS OF PATENT OWNER: LARGE ENTITY |
|
STCF | Information on status: patent grant |
Free format text: PATENTED CASE |
|
REMI | Maintenance fee reminder mailed | ||
FPAY | Fee payment |
Year of fee payment: 4 |
|
SULP | Surcharge for late payment | ||
AS | Assignment |
Owner name: GLOBALFOUNDRIES U.S. 2 LLC, NEW YORK Free format text: ASSIGNMENT OF ASSIGNORS INTEREST;ASSIGNOR:INTERNATIONAL BUSINESS MACHINES CORPORATION;REEL/FRAME:036550/0001 Effective date: 20150629 |
|
AS | Assignment |
Owner name: GLOBALFOUNDRIES INC., CAYMAN ISLANDS Free format text: ASSIGNMENT OF ASSIGNORS INTEREST;ASSIGNORS:GLOBALFOUNDRIES U.S. 2 LLC;GLOBALFOUNDRIES U.S. INC.;REEL/FRAME:036779/0001 Effective date: 20150910 |
|
FPAY | Fee payment |
Year of fee payment: 8 |
|
AS | Assignment |
Owner name: WILMINGTON TRUST, NATIONAL ASSOCIATION, DELAWARE Free format text: SECURITY AGREEMENT;ASSIGNOR:GLOBALFOUNDRIES INC.;REEL/FRAME:049490/0001 Effective date: 20181127 |
|
MAFP | Maintenance fee payment |
Free format text: PAYMENT OF MAINTENANCE FEE, 12TH YEAR, LARGE ENTITY (ORIGINAL EVENT CODE: M1553); ENTITY STATUS OF PATENT OWNER: LARGE ENTITY Year of fee payment: 12 |
|
AS | Assignment |
Owner name: GLOBALFOUNDRIES U.S. INC., CALIFORNIA Free format text: ASSIGNMENT OF ASSIGNORS INTEREST;ASSIGNOR:GLOBALFOUNDRIES INC.;REEL/FRAME:054633/0001 Effective date: 20201022 |
|
AS | Assignment |
Owner name: GLOBALFOUNDRIES INC., CAYMAN ISLANDS Free format text: RELEASE BY SECURED PARTY;ASSIGNOR:WILMINGTON TRUST, NATIONAL ASSOCIATION;REEL/FRAME:054636/0001 Effective date: 20201117 |
|
AS | Assignment |
Owner name: GLOBALFOUNDRIES U.S. INC., NEW YORK Free format text: RELEASE BY SECURED PARTY;ASSIGNOR:WILMINGTON TRUST, NATIONAL ASSOCIATION;REEL/FRAME:056987/0001 Effective date: 20201117 |